CN111694932A - Conversation method and device - Google Patents
Conversation method and device Download PDFInfo
- Publication number
- CN111694932A CN111694932A CN201910190458.0A CN201910190458A CN111694932A CN 111694932 A CN111694932 A CN 111694932A CN 201910190458 A CN201910190458 A CN 201910190458A CN 111694932 A CN111694932 A CN 111694932A
- Authority
- CN
- China
- Prior art keywords
- slot position
- slot
- information
- target
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a conversation method and device. One embodiment of the method comprises: analyzing the conversation content sent by the user by using the terminal equipment to obtain slot position information corresponding to slot positions in the slot position set; searching according to the obtained slot position information to obtain a searching result; in response to the fact that the number of the retrieval results is larger than a first preset number, for each slot in the slot position set, calculating the information entropy of the slot position according to the retrieval results; determining a target slot position according to the information entropy of each slot position in the slot position set; and sending the problem text corresponding to the target slot position to the terminal equipment. This embodiment reduces the number of user interactions.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a conversation method and device.
Background
In a self-help dialogue system (e.g., a knowledge table question-answering system or a knowledge graph system), many times a user provides only a small amount of information, the system retrieves a large number of results that meet the user's needs, but if the user is presented with such a large number of answers, the user is bothered by gathering more information to filter the results, i.e., interaction with the user is required again to reduce the number of retrieved results.
Disclosure of Invention
The embodiment of the application provides a conversation method and device.
In a first aspect, an embodiment of the present application provides a dialog method, where the method includes: analyzing the conversation content sent by the user by using the terminal equipment to obtain slot position information corresponding to slot positions in the slot position set; searching according to the obtained slot position information to obtain a searching result; in response to the fact that the number of the retrieval results is larger than a first preset number, for each slot in the slot position set, calculating the information entropy of the slot position according to the retrieval results; determining a target slot position according to the information entropy of each slot position in the slot position set; and sending the problem text corresponding to the target slot position to the terminal equipment.
In some embodiments, the method further comprises: and sending the retrieval result to the terminal equipment in response to the fact that the number of the retrieval results is smaller than or equal to the first preset number.
In some embodiments, retrieving according to the obtained slot position information to obtain a retrieval result includes: and searching in the target knowledge base according to the obtained slot position information to obtain a search result.
In some embodiments, determining the target slot from the information entropy of each slot in the set of slots comprises: and determining the slot position with the largest information entropy in the slot position set as a target slot position.
In some embodiments, determining the target slot from the information entropy of each slot in the set of slots comprises: and determining the first second preset number of slot positions with the largest information entropy in the slot position set as target slot positions.
In a second aspect, an embodiment of the present application provides a dialog apparatus, including: the analysis unit is configured to analyze the conversation content sent by the user using the terminal equipment to obtain slot position information corresponding to the slot positions in the slot position set; the retrieval unit is configured to perform retrieval according to the obtained slot position information to obtain a retrieval result; a calculation unit configured to calculate, for each slot in the slot set, an information entropy of the slot according to the search result in response to determining that the number of search results is greater than a first preset number; the determining unit is configured to determine a target slot position according to the information entropy of each slot position in the slot position set; and the first sending unit is configured to send the problem text corresponding to the target slot position to the terminal equipment.
In some embodiments, the apparatus further comprises: and the second sending unit is configured to respond to the fact that the number of the retrieval results is smaller than or equal to the first preset number, and send the retrieval results to the terminal equipment.
In some embodiments, the retrieval unit is further configured to: and searching in the target knowledge base according to the obtained slot position information to obtain a search result.
In some embodiments, the determining unit is further configured to: and determining the slot position with the largest information entropy in the slot position set as a target slot position.
In some embodiments, the determining unit is further configured to: and determining the first second preset number of slot positions with the largest information entropy in the slot position set as target slot positions.
In a third aspect, an embodiment of the present application provides a server, including: one or more processors; a storage device, on which one or more programs are stored, which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any implementation manner of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium on which a computer program is stored, where the computer program, when executed by one or more processors, implements the method as described in any implementation manner of the first aspect.
In the prior art, in multi-round dialogue interaction aiming at a knowledge form or a knowledge graph, a slot position collection process is basically fixed and determined, and each interaction needs to fix a slot position or collect slot positions according to heat or frequency. The interaction process of fixed slot position collection is not flexible and intelligent enough, and the slot position collection process can not be adjusted according to the result of conversation content returned by a user. The slot collection may be inefficient because of the excessive number of queries due to the heat or frequency.
The conversation method and the conversation device provided by the embodiment of the application analyze conversation content sent by a user through terminal equipment to obtain slot position information corresponding to slot positions in a slot position set, then search is carried out according to the obtained slot position information to obtain a search result, then in response to the fact that the number of the search result is larger than a first preset number, for each slot position in the slot position set, the information entropy of the slot position is calculated according to the search result, then a target slot position is determined according to the information entropy of each slot position in the slot position set, and finally a problem text corresponding to the target slot position is sent to the terminal equipment. Therefore, the information entropy of each slot is calculated by effectively utilizing the retrieval result, and the target slot is determined according to the information entropy of the slot to determine what question to ask the user again, and the technical effects of the method can include but are not limited to the following points:
first, the dialog process has multiple rounds of interactive capabilities: and continuously inquiring the questions of the user under the condition that the number of the retrieval results is larger than the first preset number, so that the conversation process has multi-round interaction capacity.
Second, the multi-turn conversation process is more intelligent and flexible: and under the condition that the quantity of the retrieval results is greater than the first preset quantity, continuously inquiring the user, wherein the question is determined based on the information entropy of the slot positions calculated by the retrieval results, so that the slot position collection process can be dynamically adjusted according to the conversation contents input by the user, and the multi-turn conversation process is more intelligent and flexible.
Thirdly, the resolution of the user problem is improved: the target slot position is determined according to the information entropy of the slot position, and the problem corresponding to the target slot position is sent to the terminal equipment used by the user, so that the number of retrieval results can be reduced rapidly, a proper retrieval result is provided for the user rapidly, and the resolution of the user problem is improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a conversation method in accordance with the present application;
FIG. 3 is a schematic diagram of an application scenario of a dialog method according to the present application;
FIG. 4 is a flow diagram of yet another embodiment of a conversation method in accordance with the present application;
FIG. 5 is a schematic block diagram of one embodiment of a dialogue device according to the present application;
FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows an exemplary system architecture 100 to which embodiments of the dialog method or dialog apparatus of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as a self-help conversation application, a form question and answer application, a knowledge graph application, a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, and 103 are hardware, they may be various electronic devices with a display screen, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg Audio Layer 4), laptop portable computers, desktop computers, and the like.
When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as a plurality of software or software modules (e.g. for self-service dialog services) or as a single software or software module. And is not particularly limited herein.
The server 105 may be a server providing various services, such as a background server providing support for self-help dialog applications displayed on the terminal devices 101, 102, 103. The background server may analyze and otherwise process data such as the received session request, and feed back a processing result (e.g., a search result) to the terminal device.
It should be noted that the dialogue method provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the dialogue device is generally disposed in the server 105.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a conversation method in accordance with the present application is shown. The dialogue method comprises the following steps:
In this embodiment, an execution main body of the session method (for example, a server shown in fig. 1) may first receive session content sent by a user using a terminal device, and then may parse the session content by using various natural language understanding methods, and obtain slot information corresponding to slots in a slot set.
For example, the executing agent may input the dialog content into a pre-trained BLSTM (Bi-directional long Short term memory Network) and CRF (Conditional random field) model to obtain slot information corresponding to slots in the slot set.
It will be appreciated that the corresponding set of slots may be different for different application scenarios to which the dialog method is applied. For example, for a train ticketing system, a set of slots may include the following slots: departure place, destination, one-way/round-trip, departure day, return day, train number type, train number, general/student ticket. For an alarm system, the slot set may include: time of alarm clock, repetition mode, ring of alarm clock, vibration, name of alarm clock, etc.
Here, the slot information of the slot refers to a value of a certain slot. For example, the slot information for the slot "departure place" in the train ticket booking system may be "beijing", the slot information for the slot "departure date" in the train ticket booking system may be "1 month and 5 days in 2019", and the like.
It can be understood that, the parsing of the dialog content may obtain slot information of each slot in the slot set, or may only obtain slot information of some slots in the slot set.
And step 202, retrieving according to the obtained slot position information to obtain a retrieval result.
In this embodiment, the execution body may perform a search based on the slot information of the slots in the slot set obtained in step 201, so as to obtain a search result.
For example, in the train ticket booking system, if the slot information "beijing" corresponding to the slot "departure place", the slot information "Changsha" corresponding to the slot "destination", and the slot information "2019, 1 month, 5 days" of the slot "departure date" are obtained in step 201, the execution main body may search for train ticket information having "beijing" as the departure place "," Changsha "as the destination", and "2019, 1 month, 5 days" as the search result.
In some optional implementations of this embodiment, step 202 may also be performed as follows:
and searching in the target knowledge base according to the obtained slot position information to obtain a search result. The target knowledge base may be a knowledge base corresponding to an application scenario to which the dialog method is applied. Different application scenarios may correspond to different knowledge bases. For example, for a train booking system, the target knowledge base may be a knowledge base or database related to train ticket information. For a weather query system, the target knowledge base may be a weather information-related knowledge base or database.
In this embodiment, the execution main body of the dialog method may first determine whether the number of the search results retrieved in step 202 is greater than a first preset number, and in the case that the determination is greater than the first preset number, for each slot in the slot set, calculate the information entropy of the slot according to the search result retrieved in step 202.
Here, the information entropy of the slot is used to represent the uncertainty of the slot information value of the slot.
In practice, it can be assumed that there are n values in each search result obtained in step 202 for the slot S: s1,…,Si,…,SnAnd wherein the probability corresponding to each value is respectively: p is a radical of1,…,pi,…,pnThen, the information entropy of the slot S can be calculated according to the search result by using the following formula:
where h (S) is the information entropy of the slot S obtained by calculation, and the logarithm may be based on 2 or other numbers.
And 204, determining a target slot position according to the information entropy of each slot position in the slot position set.
In step 203, the information entropy of the slot position calculated according to the search result reflects the uncertainty of the slot position information value of the slot position in the searched search result for the dialog content input by the user. It is understood that when the information uncertainty of the slot is large, the number of search results may be reduced to a large extent if the user supplements the information of the slot, and to a small extent if the information uncertainty of the slot is small. That is, the information entropy size of a slot is positively correlated with the number of search results that a user may reduce to supplement information at the slot.
Then, in this embodiment, the execution main body may determine the target slot according to the information entropy of each slot in the slot set calculated in step 203 in various implementations. Here, the target slot is a slot that requires user supplemental information, and the target slot may be one slot or a plurality of slots.
In some optional implementations of this embodiment, the execution body may determine, as the target slot, a slot in the slot set where information entropy is the largest.
In some optional implementation manners of this embodiment, the execution main body may also determine, as the target slot, a second preset number of slots in the slot set where the entropy of the information is maximum, where the second preset number is a positive integer.
In some optional implementation manners of this embodiment, the execution main body may further determine, as the target slot, a slot that is sorted second in the slot set according to the order from large to small in information entropy.
In this embodiment, the execution main body may store a problem text corresponding to each slot in the slot information set, where the problem text corresponding to each slot is a problem for the slot. For example, the question text for the slot "origin" may be "ask where do you wish to order a train ticket? ". In this way, the executing agent may send the question text corresponding to the target slot determined in step 204 to the terminal device. In this way, the terminal device can present the received question text, and then the user can see the question text and reply. The text corresponds to the target slot position, and the target slot position is determined according to the information entropy of each slot position in the slot position set. The dialog content obtained by the user replying to the question text can be sent to the execution subject to continue to execute step 201, so that the number of search results can be greatly reduced, and the user experience is improved.
With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the dialog method according to the present embodiment. In the application scenario of fig. 3, a user first inputs a dialog content 302 using a terminal device 301; then, the terminal device 301 transmits the above-mentioned conversation content 302 to the server 303 that provides support for the conversation application; then, the server 303 analyzes the conversation content 302 to obtain slot position information 304 corresponding to the slot positions in the slot position set; then, the server 303 performs retrieval according to the slot position information 304 to obtain a retrieval result 305; then, in response to determining that the number of the retrieval results 305 is greater than the first preset number, the server 303 calculates, for each slot in the slot set, an information entropy of the slot according to the retrieval results 305 to obtain an information entropy 306 of each slot in the slot set; then, the server 303 determines a target slot position 307 according to the information entropy 306 of each slot position in the slot position set; finally, the server 303 sends the question text 308 corresponding to the target slot 307 to the terminal device 301.
According to the method provided by the embodiment of the application, the information entropy of each slot position is calculated by using the retrieval result, and the target slot position is determined according to the information entropy of the slot position so as to determine the question text inquired again by the user, so that the number of the retrieval results is quickly reduced, the user can quickly obtain the retrieval results, and the user interaction times are reduced.
With further reference to fig. 4, a flow 400 of yet another embodiment of a conversation method is shown. The process 400 of the dialog method includes the following steps:
And step 402, retrieving according to the obtained slot position information to obtain a retrieval result.
In this embodiment, the specific operations of step 401 and step 402 are substantially the same as the operations of step 201 and step 202 in the embodiment shown in fig. 2, and are not described again here.
In step 403, it is determined whether the number of search results is greater than a first preset number.
In this embodiment, an executing subject of the dialog method (e.g., the server shown in fig. 1) may determine whether the number of search results obtained in step 402 is greater than a first preset number. If so, go to step 404, if not, go to step 407.
And step 404, for each slot in the slot position set, calculating the information entropy of the slot position according to the retrieval result.
And step 406, sending the problem text corresponding to the target slot position to the terminal device.
In this embodiment, the specific operations of step 404, step 405, and step 406 are substantially the same as the operations of step 203, step 204, and step 205 in the embodiment shown in fig. 2, and are not described again here.
In this embodiment, the execution subject of the dialog method (for example, the server shown in fig. 1) may directly send the search result retrieved in step 402 to the terminal device without causing trouble to the user in the case that it is determined in step 403 that the number of search results is not greater than the first preset number, that is, in the case that the number of search results is not so large.
As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the process 400 of the dialog method in this embodiment has more steps of directly sending the search result to the terminal device when the number of the search results is not greater than the first preset number. Therefore, the scheme described in the embodiment can realize more comprehensive conversation process.
With further reference to fig. 5, as an implementation of the method shown in the above figures, the present application provides an embodiment of a dialog apparatus, which corresponds to the embodiment of the method shown in fig. 2, and which may be applied in various electronic devices.
As shown in fig. 5, the dialogue device 500 of the present embodiment includes: analysis section 501, search section 502, calculation section 503, determination section 504, and first transmission section 505. The analyzing unit 501 is configured to analyze the session content sent by the user using the terminal device to obtain slot position information corresponding to the slot position in the slot position set; a retrieval unit 502 configured to perform retrieval according to the obtained slot position information to obtain a retrieval result; a calculating unit 503 configured to, for each slot in the slot set, calculate an information entropy of the slot according to the search result in response to determining that the number of the search results is greater than a first preset number; a determining unit 504 configured to determine a target slot according to the information entropy of each slot in the slot set; a first sending unit 505 configured to send the problem text corresponding to the target slot to the terminal device.
In this embodiment, the detailed processing of the parsing unit 501, the retrieving unit 502, the calculating unit 503, the determining unit 504, and the first sending unit 505 of the dialog apparatus 500 and the technical effects thereof can refer to the related descriptions of step 201, step 202, step 203, step 204, and step 205 in the corresponding embodiment of fig. 2, which are not repeated herein.
In some optional implementations of this embodiment, the apparatus 500 may further include: a second sending unit 506, configured to send the search result to the terminal device in response to determining that the number of the search results is less than or equal to the first preset number.
In some optional implementations of this embodiment, the retrieving unit 502 may be further configured to: and searching in the target knowledge base according to the obtained slot position information to obtain a search result.
In some optional implementations of this embodiment, the determining unit 504 may be further configured to: and determining the slot position with the largest information entropy in the slot position set as the target slot position.
In some optional implementations of this embodiment, the determining unit 504 may be further configured to: and determining the first second preset number of slot positions with the largest information entropy in the slot position set as the target slot position.
It should be noted that details of implementation and technical effects of each unit in the dialog apparatus provided in the embodiment of the present application may refer to descriptions of other embodiments in the present application, and are not described herein again.
Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a server according to embodiments of the present application. The server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM602, and RAM 603 are connected to each other via a bus 604. An Input/Output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output section 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN (Local area network) card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a parsing unit, a retrieval unit, a calculation unit, a determination unit, and a first transmission unit. The names of these units do not in some cases form a limitation on the unit itself, and for example, a parsing unit may also be described as a "unit that parses the dialog content to obtain slot information".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: analyzing the conversation content sent by the user by using the terminal equipment to obtain slot position information corresponding to slot positions in the slot position set; searching according to the obtained slot position information to obtain a searching result; in response to the fact that the number of the retrieval results is larger than a first preset number, for each slot in the slot position set, calculating the information entropy of the slot position according to the retrieval results; determining a target slot position according to the information entropy of each slot position in the slot position set; and sending the problem text corresponding to the target slot position to the terminal equipment.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (12)
1. A conversation method comprising:
analyzing the conversation content sent by the user by using the terminal equipment to obtain slot position information corresponding to slot positions in the slot position set;
searching according to the obtained slot position information to obtain a searching result;
in response to the fact that the number of the retrieval results is larger than a first preset number, for each slot position in the slot position set, calculating the information entropy of the slot position according to the retrieval results;
determining a target slot position according to the information entropy of each slot position in the slot position set;
and sending the problem text corresponding to the target slot position to the terminal equipment.
2. The method of claim 1, wherein the method further comprises:
and sending the retrieval result to the terminal equipment in response to the fact that the number of the retrieval results is smaller than or equal to the first preset number.
3. The method of claim 1, wherein the retrieving according to the obtained slot position information to obtain a retrieval result comprises:
and searching in the target knowledge base according to the obtained slot position information to obtain a search result.
4. The method of any of claims 1-3, wherein the determining a target slot from an entropy of information for each slot in the set of slots comprises:
and determining the slot position with the largest information entropy in the slot position set as the target slot position.
5. The method of any of claims 1-3, wherein the determining a target slot from an entropy of information for each slot in the set of slots comprises:
and determining the first second preset number of slot positions with the largest information entropy in the slot position set as the target slot position.
6. A conversation apparatus comprising:
the analysis unit is configured to analyze the conversation content sent by the user using the terminal equipment to obtain slot position information corresponding to the slot positions in the slot position set;
the retrieval unit is configured to perform retrieval according to the obtained slot position information to obtain a retrieval result;
a calculating unit configured to calculate, for each slot in the slot set, an information entropy of the slot according to the retrieval result in response to determining that the number of the retrieval results is greater than a first preset number;
a determining unit configured to determine a target slot position according to the information entropy of each slot position in the slot position set;
and the first sending unit is configured to send the problem text corresponding to the target slot position to the terminal equipment.
7. The apparatus of claim 6, wherein the apparatus further comprises:
a second sending unit configured to send the retrieval result to the terminal device in response to determining that the number of the retrieval results is less than or equal to the first preset number.
8. The apparatus of claim 6, wherein the retrieval unit is further configured to:
and searching in the target knowledge base according to the obtained slot position information to obtain a search result.
9. The apparatus according to any of claims 6-8, wherein the determining unit is further configured to:
and determining the slot position with the largest information entropy in the slot position set as the target slot position.
10. The apparatus according to any of claims 6-8, wherein the determining unit is further configured to:
and determining the first second preset number of slot positions with the largest information entropy in the slot position set as the target slot position.
11. A server, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-5.
12. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by one or more processors, implements the method of any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910190458.0A CN111694932A (en) | 2019-03-13 | 2019-03-13 | Conversation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910190458.0A CN111694932A (en) | 2019-03-13 | 2019-03-13 | Conversation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111694932A true CN111694932A (en) | 2020-09-22 |
Family
ID=72475846
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910190458.0A Pending CN111694932A (en) | 2019-03-13 | 2019-03-13 | Conversation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111694932A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114722152A (en) * | 2022-04-15 | 2022-07-08 | 贝壳找房网(北京)信息技术有限公司 | Interactive search method and device |
CN115577089A (en) * | 2022-11-24 | 2023-01-06 | 零犀(北京)科技有限公司 | Method, device, equipment and storage medium for optimizing nodes in conversation process |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101356525A (en) * | 2005-11-30 | 2009-01-28 | 微软公司 | Adaptive semantic reasoning engine |
CN104360897A (en) * | 2014-10-29 | 2015-02-18 | 百度在线网络技术(北京)有限公司 | Conversation processing method and conversation management system |
GB201701918D0 (en) * | 2017-02-06 | 2017-03-22 | Toshiba Kk | A spoken dialogue system, a spoken dialogue method and a method of adapting a spoken dialogue system |
CN107480162A (en) * | 2017-06-15 | 2017-12-15 | 北京百度网讯科技有限公司 | Searching method, device, equipment and computer-readable recording medium based on artificial intelligence |
CN107577689A (en) * | 2016-07-04 | 2018-01-12 | 松下知识产权经营株式会社 | Decision tree generating means, decision tree generation method, non-transitory recording medium and enquirement system |
CN108228637A (en) * | 2016-12-21 | 2018-06-29 | 中国电信股份有限公司 | Natural language client auto-answer method and system |
CN108287901A (en) * | 2018-01-24 | 2018-07-17 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
CN108776692A (en) * | 2018-06-06 | 2018-11-09 | 北京京东尚科信息技术有限公司 | Method and apparatus for handling information |
CN108922531A (en) * | 2018-07-26 | 2018-11-30 | 腾讯科技(深圳)有限公司 | Slot position recognition methods, device, electronic equipment and storage medium |
-
2019
- 2019-03-13 CN CN201910190458.0A patent/CN111694932A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101356525A (en) * | 2005-11-30 | 2009-01-28 | 微软公司 | Adaptive semantic reasoning engine |
CN104360897A (en) * | 2014-10-29 | 2015-02-18 | 百度在线网络技术(北京)有限公司 | Conversation processing method and conversation management system |
CN107577689A (en) * | 2016-07-04 | 2018-01-12 | 松下知识产权经营株式会社 | Decision tree generating means, decision tree generation method, non-transitory recording medium and enquirement system |
CN108228637A (en) * | 2016-12-21 | 2018-06-29 | 中国电信股份有限公司 | Natural language client auto-answer method and system |
GB201701918D0 (en) * | 2017-02-06 | 2017-03-22 | Toshiba Kk | A spoken dialogue system, a spoken dialogue method and a method of adapting a spoken dialogue system |
CN107480162A (en) * | 2017-06-15 | 2017-12-15 | 北京百度网讯科技有限公司 | Searching method, device, equipment and computer-readable recording medium based on artificial intelligence |
CN108287901A (en) * | 2018-01-24 | 2018-07-17 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
CN108776692A (en) * | 2018-06-06 | 2018-11-09 | 北京京东尚科信息技术有限公司 | Method and apparatus for handling information |
CN108922531A (en) * | 2018-07-26 | 2018-11-30 | 腾讯科技(深圳)有限公司 | Slot position recognition methods, device, electronic equipment and storage medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114722152A (en) * | 2022-04-15 | 2022-07-08 | 贝壳找房网(北京)信息技术有限公司 | Interactive search method and device |
CN115577089A (en) * | 2022-11-24 | 2023-01-06 | 零犀(北京)科技有限公司 | Method, device, equipment and storage medium for optimizing nodes in conversation process |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
CN107679211B (en) | Method and device for pushing information | |
CN109522483B (en) | Method and device for pushing information | |
US11758088B2 (en) | Method and apparatus for aligning paragraph and video | |
CN108536867B (en) | Method and apparatus for generating information | |
JP2021103506A (en) | Method and device for generating information | |
CN110866040B (en) | User portrait generation method, device and system | |
US11706172B2 (en) | Method and device for sending information | |
US20200409998A1 (en) | Method and device for outputting information | |
CN108600780B (en) | Method for pushing information, electronic device and computer readable medium | |
CN111274490A (en) | Method and device for processing consultation information | |
CN110399459B (en) | Online document searching method, device, terminal, server and storage medium | |
CN111694932A (en) | Conversation method and device | |
CN107885872B (en) | Method and device for generating information | |
CN111581356B (en) | User behavior path analysis method and device | |
CN111124858B (en) | Buried point-free insertion code data processing method, system, terminal equipment and storage medium | |
KR20210080561A (en) | Consulting information processing method and device | |
CN110971983B (en) | Video question answering method, equipment and storage medium | |
CN111125502B (en) | Method and device for generating information | |
CN110110032B (en) | Method and device for updating index file | |
CN112307324B (en) | Information processing method, device, equipment and medium | |
CN110881056A (en) | Method and device for pushing information | |
CN111131354B (en) | Method and apparatus for generating information | |
CN111125501B (en) | Method and device for processing information | |
WO2020078049A1 (en) | User information processing method and device, server, and readable medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |